Fetch MCP
A template for deploying remote Model Context Protocol servers on Cloudflare Workers using Server-Sent Events without authentication. It enables users to host custom tools on the edge and connect them to clients like Claude Desktop or the Cloudflare
What is Fetch MCP?
Fetch MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to template for deploying remote model context protocol servers on cloudflare workers using server-sent events without authentication. it enables users to host custom tools on the edge and connect them t...
A template for deploying remote Model Context Protocol servers on Cloudflare Workers using Server-Sent Events without authentication. It enables users to host custom tools on the edge and connect them to clients like Claude Desktop or the Cloudflare
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A template for deploying remote Model Context Protocol serve
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx fetch-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Fetch MCP
Fetcher MCP is a web content retrieval MCP server that uses Playwright with a headless Chromium browser to fetch any URL — including JavaScript-heavy single-page applications that basic HTTP clients cannot scrape. It exposes three tools: `fetch_url` for single-page retrieval, `fetch_urls` for parallel batch fetching, and `browser_install` for automated Chromium setup. Claude and other MCP clients use it to read live web pages, extract structured content, and process sites that require full browser execution.
Prerequisites
- Node.js 18 or later
- npx available (bundled with Node.js)
- Chromium installed via Playwright (`npx playwright install chromium`) — the server attempts auto-install on first run
- An MCP-compatible client such as Claude Desktop
- Sufficient disk space for the Chromium binary (~200 MB)
Install Playwright Chromium
Install the Chromium browser that Fetcher MCP drives. This is a one-time setup step; the server will also attempt this automatically on first launch.
npx playwright install chromiumTest the server manually
Run the server directly with npx to confirm it starts without errors before adding it to your MCP client.
npx -y fetcher-mcpConfigure Claude Desktop
Add the fetcher server to your Claude Desktop MCP configuration. No API keys or environment variables are required.
Restart Claude Desktop
Restart Claude Desktop so the new MCP server is registered. The fetcher tool will appear in the tool list automatically.
(Optional) Run as an HTTP/SSE server
To expose Fetcher MCP over the network — for example, to connect from a remote client — start it with HTTP transport mode.
npx -y fetcher-mcp --transport=http --host=0.0.0.0 --port=3000(Optional) Deploy via Docker
For production or containerized environments, pull and run the official Docker image.
docker run -p 3000:3000 ghcr.io/jae-jae/fetcher-mcp:latestFetch MCP Examples
Client configuration
Minimal Claude Desktop configuration for Fetcher MCP using npx. No environment variables are required.
{
"mcpServers": {
"fetcher": {
"command": "npx",
"args": ["-y", "fetcher-mcp"]
}
}
}Prompts to try
Sample prompts for using Fetcher MCP inside Claude Desktop.
- "Fetch the content of https://example.com and summarize the main points."
- "Retrieve these three URLs in parallel and compare their content: [url1], [url2], [url3]."
- "Fetch https://news.ycombinator.com and list the top 10 headlines with their scores."
- "Get the full HTML of https://myapp.com/docs and extract all the API endpoint names."
- "Fetch this React app page and wait for the dynamic content to load before extracting the product list."Troubleshooting Fetch MCP
Error: browserType.launch: Executable doesn't exist
Run `npx playwright install chromium` to download the browser binary. If the server is run by a different user (e.g., Claude Desktop uses a separate process), run the install command as that user or set the `PLAYWRIGHT_BROWSERS_PATH` environment variable to a shared writable location.
Pages with JavaScript return empty or incomplete content
Tell Claude to wait for the page to fully load: 'Please wait until the page is fully loaded before extracting content.' This instructs the `fetch_url` tool to use `waitUntil: networkidle` internally.
Fetching times out on slow sites
Ask Claude to increase the timeout: 'Please set the page loading timeout to 60 seconds.' The tool accepts a `timeout` parameter in milliseconds. For very slow sites, also try disabling media loading by asking Claude to 'disable media loading for this fetch.'
Frequently Asked Questions about Fetch MCP
What is Fetch MCP?
Fetch MCP is a Model Context Protocol (MCP) server that template for deploying remote model context protocol servers on cloudflare workers using server-sent events without authentication. it enables users to host custom tools on the edge and connect them to clients like claude desktop or the cloudflare It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Fetch MCP?
Follow the installation instructions on the Fetch MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Fetch MCP?
Fetch MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Fetch MCP free to use?
Yes, Fetch MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Fetch MCP Alternatives — Similar Cloud Services Servers
Looking for alternatives to Fetch MCP? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Fetch MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Fetch MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.